An efficient model for auxiliary diagnosis of hepatocellular carcinoma based on gene expression programming

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related death worldwide. The early diagnosis of HCC is greatly helpful to achieve long-term disease-free survival. However, HCC is usually difficult to be diagnosed at an early stage. The aim of this study was to create the prediction model...

Full description

Saved in:
Bibliographic Details
Published in:Medical & biological engineering & computing Vol. 56; no. 10; pp. 1771 - 1779
Main Authors: Zhang, Li, Chen, Jiasheng, Gao, Chunming, Liu, Chuanmiao, Xu, Kuihua
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2018
Springer Nature B.V
Subjects:
Adult
Aged
Aged, 80 and over
Algorithms
Antigens
Artificial Intelligence
Artificial neural networks
Biomarkers
Biomarkers, Tumor - blood
Biomedical and Life Sciences
Biomedical Engineering and Bioengineering
Biomedicine
Carbohydrates
Carcinoembryonic antigen
Carcinoma, Hepatocellular - blood
Carcinoma, Hepatocellular - diagnosis
Carcinoma, Hepatocellular - genetics
Case-Control Studies
Computer Applications
Diagnosis
Evolutionary algorithms
Female
Gene expression
Gene Expression Regulation, Neoplastic
Hepatocellular carcinoma
Human Physiology
Humans
Imaging
Liver cancer
Liver Neoplasms - blood
Liver Neoplasms - diagnosis
Liver Neoplasms - genetics
Male
Mathematical models
Medical diagnosis
Middle Aged
Multilayer perceptrons
Neural networks
Original Article
Problem solving
Radiology
ROC Curve
Test sets
Young Adult
α-Fetoprotein
γ-Glutamyltransferase
Hepatocellular carcinoma
Auxiliary diagnosis
Serum biomarkers
Gene expression programming
ISSN:0140-0118, 1741-0444, 1741-0444
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hepatocellular carcinoma (HCC) is a leading cause of cancer-related death worldwide. The early diagnosis of HCC is greatly helpful to achieve long-term disease-free survival. However, HCC is usually difficult to be diagnosed at an early stage. The aim of this study was to create the prediction model to diagnose HCC based on gene expression programming (GEP). GEP is an evolutionary algorithm and a domain-independent problem-solving technique. Clinical data show that six serum biomarkers, including gamma-glutamyl transferase, C-reaction protein, carcinoembryonic antigen, alpha-fetoprotein, carbohydrate antigen 153, and carbohydrate antigen 199, are related to HCC characteristics. In this study, the prediction of HCC was made based on these six biomarkers (195 HCC patients and 215 non-HCC controls) by setting up optimal joint models with GEP. The GEP model discriminated 353 out of 410 subjects, representing a determination coefficient of 86.28% (283/328) and 85.37% (70/82) for training and test sets, respectively. Compared to the results from the support vector machine, the artificial neural network, and the multilayer perceptron, GEP showed a better outcome. The results suggested that GEP modeling was a promising and excellent tool in diagnosis of hepatocellular carcinoma, and it could be widely used in HCC auxiliary diagnosis. Graphical abstract The process to establish an efficient model for auxiliary diagnosis of hepatocellular carcinoma
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0140-0118
1741-0444
1741-0444
DOI:10.1007/s11517-018-1811-6